add fast matmul iquants (#22504)

This commit is contained in:
Rithik Sharma
2026-04-29 22:58:32 -07:00
committed by GitHub
parent 80afa33aad
commit 45155597aa
3 changed files with 443 additions and 1 deletions
+1 -1
View File
@@ -1422,7 +1422,7 @@ static webgpu_encoded_op ggml_webgpu_mul_mat(webgpu_context & ctx,
case GGML_TYPE_IQ3_S:
case GGML_TYPE_IQ4_NL:
case GGML_TYPE_IQ4_XS:
use_fast = is_vec;
use_fast = true;
break;
default:
break;